Grammalecte  Check-in [4078670807]

Overview
Comment:[core][fr] split core tests and modules test
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | fr | core
Files: files | file ages | folders
SHA3-256: 40786708073e38345f7ba5410c7cfe53ec04b0abb507bc7ef90777f6677be114
User & Date: olr on 2020-07-31 11:47:28
Other Links: manifest | tags
Context
2020-07-31
12:03
[build] clearer information while building check-in: d3a1bb04cc user: olr tags: trunk, build
11:47
[core][fr] split core tests and modules test check-in: 4078670807 user: olr tags: trunk, fr, core
10:03
[fx] iframe edition now available check-in: 45e4affdff user: olr tags: trunk, major_change, fx
Changes

Added gc_core/py/lang_core/tests_core.py version [ccfe3a8352].











































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
#! python3

"""
Grammar checker tests for French language
"""

import unittest
import os
import re
import time
from contextlib import contextmanager


from ..graphspell.echo import echo
from . import gc_engine


@contextmanager
def timeblock (label, hDst):
    "performance counter (contextmanager)"
    start = time.perf_counter()
    try:
        yield
    finally:
        end = time.perf_counter()
        print('{} : {}'.format(label, end - start))
        if hDst:
            hDst.write("{:<12.6}".format(end-start))


def perf (sVersion, bMemo=False):
    "performance tests"
    print("Performance tests")
    gc_engine.load()
    gc_engine.parse("Text to compile rules before launching real tests.")

    spHere, _ = os.path.split(__file__)
    spfPerfTest = os.path.join(spHere, "perf.txt")
    if not os.path.exists(spfPerfTest):
        print(f"No file <perf.txt> in <{spHere}>")
        return
    with open(spfPerfTest, "r", encoding="utf-8") as hSrc:
        hDst = open("./gc_lang/"+sLang+"/perf_memo.txt", "a", encoding="utf-8", newline="\n")  if bMemo  else None
        if hDst:
            hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M")))
        for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ):
            with timeblock(sText[:sText.find(".")], hDst):
                gc_engine.parse(sText)
        if hDst:
            hDst.write("\n")


def _fuckBackslashUTF8 (s):
    "fuck that shit"
    return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—")


class TestGrammarChecking (unittest.TestCase):
    "Tests du correcteur grammatical"

    @classmethod
    def setUpClass (cls):
        gc_engine.load()
        cls._zError = re.compile(r"\{\{.*?\}\}")
        cls._aTestedRules = set()

    def test_parse (self):
        zOption = re.compile("^__([a-zA-Z0-9]+)__ ")
        spHere, _ = os.path.split(__file__)
        spfParsingTest = os.path.join(spHere, "gc_test.txt")
        if not os.path.exists(spfParsingTest):
            print(f"No file <gc_test.txt> in <{spHere}>")
            return
        with open(spfParsingTest, "r", encoding="utf-8") as hSrc:
            nError = 0
            for sLine in ( s for s in hSrc if not s.startswith("#") and s.strip() ):
                sLineNum = sLine[:10].strip()
                sLine = sLine[10:].strip()
                sOption = None
                m = zOption.search(sLine)
                if m:
                    sLine = sLine[m.end():]
                    sOption = m.group(1)
                if "->>" in sLine:
                    sErrorText, sExceptedSuggs = self._splitTestLine(sLine)
                    if sExceptedSuggs.startswith('"') and sExceptedSuggs.endswith('"'):
                        sExceptedSuggs = sExceptedSuggs[1:-1]
                else:
                    sErrorText = sLine.strip()
                    sExceptedSuggs = ""
                sExpectedErrors = self._getExpectedErrors(sErrorText)
                sTextToCheck = sErrorText.replace("}}", "").replace("{{", "")
                sFoundErrors, sListErr, sFoundSuggs = self._getFoundErrors(sTextToCheck, sOption)
                # tests
                if sExpectedErrors != sFoundErrors:
                    print("\n# Line num: " + sLineNum + \
                          "\n> to check: " + _fuckBackslashUTF8(sTextToCheck) + \
                          "\n  expected: " + sExpectedErrors + \
                          "\n  found:    " + sFoundErrors + \
                          "\n  errors:   \n" + sListErr)
                    nError += 1
                elif sExceptedSuggs:
                    if sExceptedSuggs != sFoundSuggs:
                        print("\n# Line num: " + sLineNum + \
                              "\n> to check: " + _fuckBackslashUTF8(sTextToCheck) + \
                              "\n  expected: " + sExceptedSuggs + \
                              "\n  found:    " + sFoundSuggs + \
                              "\n  errors:   \n" + sListErr)
                        nError += 1
            if nError:
                print("Unexpected errors:", nError)
        # untested rules
        aUntestedRules = set()
        for _, sOpt, sLineId, sRuleId in gc_engine.listRules():
            sRuleId = sRuleId.rstrip("0123456789")
            if sOpt != "@@@@" and sRuleId not in self._aTestedRules and not re.search("^[0-9]+[sp]$|^[pd]_", sRuleId):
                aUntestedRules.add(f"{sLineId}/{sRuleId}")
        if aUntestedRules:
            print()
            for sRule in aUntestedRules:
                echo(sRule)
            echo("  [{} untested rules]".format(len(aUntestedRules)))

    def _splitTestLine (self, sLine):
        sText, sSugg = sLine.split("->>")
        return (sText.strip(), sSugg.strip())

    def _getFoundErrors (self, sLine, sOption):
        if sOption:
            gc_engine.setOption(sOption, True)
            aErrs = gc_engine.parse(sLine)
            gc_engine.setOption(sOption, False)
        else:
            aErrs = gc_engine.parse(sLine)
        sRes = " " * len(sLine)
        sListErr = ""
        lAllSugg = []
        for dErr in aErrs:
            sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
            sListErr += "    * {sLineId} / {sRuleId}  at  {nStart}:{nEnd}\n".format(**dErr)
            lAllSugg.append("|".join(dErr["aSuggestions"]))
            self._aTestedRules.add(dErr["sRuleId"].rstrip("0123456789"))
            # test messages
            if "<start>" in dErr["sMessage"] or "<end>" in dErr["sMessage"]:
                print("\n# Line num : " + dErr["sLineId"] + \
                      "\n  rule name: " + dErr["sRuleId"] + \
                      "\n  message  : " + dErr["sMessage"])
        return sRes, sListErr, "|||".join(lAllSugg)

    def _getExpectedErrors (self, sLine):
        sRes = " " * len(sLine)
        for i, m in enumerate(self._zError.finditer(sLine)):
            nStart = m.start() - (4 * i)
            nEnd = m.end() - (4 * (i+1))
            sRes = sRes[:nStart] + "~" * (nEnd - nStart) + sRes[nEnd:-4]
        return sRes


def main():
    "start function"
    unittest.main()


if __name__ == '__main__':
    main()

Modified gc_lang/fr/modules/tests_modules.py from [a7f5c21eb9] to [f6de09e840].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
#! python3

"""
Grammar checker tests for French language
"""

import unittest
import os
import re
import time
from contextlib import contextmanager

from ..graphspell.ibdawg import IBDAWG
from ..graphspell.echo import echo
from . import gc_engine as gce
from . import conj
from . import phonet
from . import mfsp


@contextmanager
def timeblock (label, hDst):
    "performance counter (contextmanager)"
    start = time.perf_counter()
    try:
        yield
    finally:
        end = time.perf_counter()
        print('{} : {}'.format(label, end - start))
        if hDst:
            hDst.write("{:<12.6}".format(end-start))


def perf (sVersion, hDst=None):
    "performance tests"
    print("\nPerformance tests")
    gce.load()
    gce.parse("Texte sans importance… utile pour la compilation des règles avant le calcul des perfs.")

    spHere, _ = os.path.split(__file__)
    with open(os.path.join(spHere, "perf.txt"), "r", encoding="utf-8") as hSrc:
        if hDst:
            hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M")))
        for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ):
            with timeblock(sText[:sText.find(".")], hDst):
                gce.parse(sText)
        if hDst:
            hDst.write("\n")


def _fuckBackslashUTF8 (s):
    "fuck that shit"
    return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—")


class TestDictionary (unittest.TestCase):
    "Test du correcteur orthographique"

    @classmethod
    def setUpClass (cls):
        cls.oDic = IBDAWG("${dic_main_filename_py}")










<



<




<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







1
2
3
4
5
6
7
8
9
10

11
12
13

14
15
16
17



































18
19
20
21
22
23
24
#! python3

"""
Grammar checker tests for French language
"""

import unittest
import os
import re
import time


from ..graphspell.ibdawg import IBDAWG
from ..graphspell.echo import echo

from . import conj
from . import phonet
from . import mfsp





































class TestDictionary (unittest.TestCase):
    "Test du correcteur orthographique"

    @classmethod
    def setUpClass (cls):
        cls.oDic = IBDAWG("${dic_main_filename_py}")
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
            ("gentleman", ["gentlemans", "gentlemen"])
        ]

    def test_getplural (self):
        for sSing, lPlur in self.lPlural:
            self.assertListEqual(mfsp.getMiscPlural(sSing), lPlur)


class TestGrammarChecking (unittest.TestCase):
    "Tests du correcteur grammatical"

    @classmethod
    def setUpClass (cls):
        gce.load()
        cls._zError = re.compile(r"\{\{.*?\}\}")
        cls._aTestedRules = set()

    def test_parse (self):
        zOption = re.compile("^__([a-zA-Z0-9]+)__ ")
        spHere, _ = os.path.split(__file__)
        with open(os.path.join(spHere, "gc_test.txt"), "r", encoding="utf-8") as hSrc:
            nError = 0
            for sLine in ( s for s in hSrc if not s.startswith("#") and s.strip() ):
                sLineNum = sLine[:10].strip()
                sLine = sLine[10:].strip()
                sOption = None
                m = zOption.search(sLine)
                if m:
                    sLine = sLine[m.end():]
                    sOption = m.group(1)
                if "->>" in sLine:
                    sErrorText, sExceptedSuggs = self._splitTestLine(sLine)
                    if sExceptedSuggs.startswith('"') and sExceptedSuggs.endswith('"'):
                        sExceptedSuggs = sExceptedSuggs[1:-1]
                else:
                    sErrorText = sLine.strip()
                    sExceptedSuggs = ""
                sExpectedErrors = self._getExpectedErrors(sErrorText)
                sTextToCheck = sErrorText.replace("}}", "").replace("{{", "")
                sFoundErrors, sListErr, sFoundSuggs = self._getFoundErrors(sTextToCheck, sOption)
                # tests
                if sExpectedErrors != sFoundErrors:
                    print("\n# Line num: " + sLineNum + \
                          "\n> to check: " + _fuckBackslashUTF8(sTextToCheck) + \
                          "\n  expected: " + sExpectedErrors + \
                          "\n  found:    " + sFoundErrors + \
                          "\n  errors:   \n" + sListErr)
                    nError += 1
                elif sExceptedSuggs:
                    if sExceptedSuggs != sFoundSuggs:
                        print("\n# Line num: " + sLineNum + \
                              "\n> to check: " + _fuckBackslashUTF8(sTextToCheck) + \
                              "\n  expected: " + sExceptedSuggs + \
                              "\n  found:    " + sFoundSuggs + \
                              "\n  errors:   \n" + sListErr)
                        nError += 1
            if nError:
                print("Unexpected errors:", nError)
        # untested rules
        aUntestedRules = set()
        for _, sOpt, sLineId, sRuleId in gce.listRules():
            sRuleId = sRuleId.rstrip("0123456789")
            if sOpt != "@@@@" and sRuleId not in self._aTestedRules and not re.search("^[0-9]+[sp]$|^[pd]_", sRuleId):
                aUntestedRules.add(f"{sLineId}/{sRuleId}")
        if aUntestedRules:
            print()
            for sRule in aUntestedRules:
                echo(sRule)
            echo("  [{} untested rules]".format(len(aUntestedRules)))

    def _splitTestLine (self, sLine):
        sText, sSugg = sLine.split("->>")
        return (sText.strip(), sSugg.strip())

    def _getFoundErrors (self, sLine, sOption):
        if sOption:
            gce.setOption(sOption, True)
            aErrs = gce.parse(sLine)
            gce.setOption(sOption, False)
        else:
            aErrs = gce.parse(sLine)
        sRes = " " * len(sLine)
        sListErr = ""
        lAllSugg = []
        for dErr in aErrs:
            sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
            sListErr += "    * {sLineId} / {sRuleId}  at  {nStart}:{nEnd}\n".format(**dErr)
            lAllSugg.append("|".join(dErr["aSuggestions"]))
            self._aTestedRules.add(dErr["sRuleId"].rstrip("0123456789"))
            # test messages
            if "<start>" in dErr["sMessage"] or "<end>" in dErr["sMessage"]:
                print("\n# Line num : " + dErr["sLineId"] + \
                      "\n  rule name: " + dErr["sRuleId"] + \
                      "\n  message  : " + dErr["sMessage"])
        return sRes, sListErr, "|||".join(lAllSugg)

    def _getExpectedErrors (self, sLine):
        sRes = " " * len(sLine)
        for i, m in enumerate(self._zError.finditer(sLine)):
            nStart = m.start() - (4 * i)
            nEnd = m.end() - (4 * (i+1))
            sRes = sRes[:nStart] + "~" * (nEnd - nStart) + sRes[nEnd:-4]
        return sRes


def main():
    "start function"
    unittest.main()


if __name__ == '__main__':
    main()








<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







111
112
113
114
115
116
117
118

































































































119
120
121
122
123
124
125
            ("gentleman", ["gentlemans", "gentlemen"])
        ]

    def test_getplural (self):
        for sSing, lPlur in self.lPlural:
            self.assertListEqual(mfsp.getMiscPlural(sSing), lPlur)



































































































def main():
    "start function"
    unittest.main()


if __name__ == '__main__':
    main()

Modified make.py from [e02d3d08f6] to [edc705fbf3].

429
430
431
432
433
434
435
436
437
438






439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
            bUseCache = None            # we may rebuild if it’s necessary
            if xArgs.use_cache:
                bUseCache = True        # we use the cache if it exists
            if xArgs.force_rebuild:
                bUseCache = False       # we rebuild
            sVersion = create(sLang, xConfig, xArgs.install, xArgs.javascript, bUseCache)

            # tests
            if xArgs.tests or xArgs.perf or xArgs.perf_memo:
                print("> Running tests")






                try:
                    tests = importlib.import_module("grammalecte."+sLang+".tests")
                    print(tests.__file__)
                except ImportError:
                    print(f"# Error. Import failed: grammalecte.{sLang}.tests")
                    traceback.print_exc()
                else:
                    if xArgs.tests:
                        xTestSuite = unittest.TestLoader().loadTestsFromModule(tests)
                        unittest.TextTestRunner().run(xTestSuite)
                    if xArgs.perf or xArgs.perf_memo:
                        hDst = open("./gc_lang/"+sLang+"/perf_memo.txt", "a", encoding="utf-8", newline="\n")  if xArgs.perf_memo  else None
                        tests.perf(sVersion, hDst)

            # JavaScript linter
            if xArgs.lint_web_ext:
                with helpers.CD("_build/webext/"+sLang):
                    os.system(r'web-ext lint -o text')

            # Firefox







|
|

>
>
>
>
>
>

|
<

|
<

<
<
<
<
<
|







429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446

447
448

449





450
451
452
453
454
455
456
457
            bUseCache = None            # we may rebuild if it’s necessary
            if xArgs.use_cache:
                bUseCache = True        # we use the cache if it exists
            if xArgs.force_rebuild:
                bUseCache = False       # we rebuild
            sVersion = create(sLang, xConfig, xArgs.install, xArgs.javascript, bUseCache)

            # Tests
            if xArgs.tests:
                print("> Running tests")
                lTestModules = [f"grammalecte.{sLang}.tests_core", \
                                f"grammalecte.{sLang}.tests_modules"]
                xTestSuite = unittest.TestLoader().loadTestsFromNames(lTestModules)
                unittest.TextTestRunner().run(xTestSuite)

            if xArgs.perf or xArgs.perf_memo:
                try:
                    tests = importlib.import_module(f"grammalecte.{sLang}.tests_core")

                except ImportError:
                    print(f"# Error. Import failed: grammalecte.{sLang}.tests_core")

                else:





                    tests.perf(sVersion, xArgs.perf_memo)

            # JavaScript linter
            if xArgs.lint_web_ext:
                with helpers.CD("_build/webext/"+sLang):
                    os.system(r'web-ext lint -o text')

            # Firefox